Can I run it?
Can I run Qwen3.8 27B on Apple M3 Pro?
Tight fit
Tight fit fully in unified memory on your Apple M3 Pro at UD-IQ3_S, 8K context, about 6.6–8.9 tok/s. Weights 11.2 GB plus 0.57 GB of KV cache — 12.2 GB of 13.0 GB usable. Up to 16K context still fits.
Best quantUD-IQ3_S
Working context8K
Max that fits16K
Speed6.6–8.9 tok/sEstimate from memory bandwidth, not a benchmark. Method.
Weights11.2 GB
KV cache0.57 GB
Total12.2 GB
Usable13.0 GB
Qwen3.8 27B details · Apple M3 Pro page · How this estimate is made
Run commands
llama.cpp
llama-server -hf unsloth/Qwen3.8-27B-GGUF:UD-IQ3_S -c 8192 -ngl 64
Ollama
ollama run qwen3.8
LM Studio
lms get unsloth/Qwen3.8-27B-GGUF # Then load quant UD-IQ3_S
Assumptions
- Estimate from memory bandwidth, not a benchmark. Decode speed uses 55–75% of peak bandwidth.
- KV cache is FP16. Engine overhead assumes llama.cpp (0.3 GB + 1% of the weights). Ollama is closer to 0.9 GB + 3%, LM Studio closer to 1 GB + 3%.
- UD-IQ3_S size is the real GGUF file size from Hugging Face.
- Unified memory uses 75% for the GPU by default, and always leaves about 5 GB for the OS.
- Speed is quoted at 8K context, not at the maximum context that still fits.
Larger models that also fit
- Can I run Qwen3.6 35B A3B on Apple M3 Pro? — Tight fit, UD-Q2_K_XL, 16–22 tok/s (estimate)
- Can I run Qwen3.5 35B A3B on Apple M3 Pro? — Tight fit, UD-IQ3_XXS, 15–21 tok/s (estimate)
- Can I run Qwen2.5 32B Instruct on Apple M3 Pro? — Heavily degraded, IQ2_S, 6.6–9.0 tok/s (estimate)
Updated 2026-10-24. Profile on this page is the device default.